When to Use
Use this skill when:
- Starting a new project and need to identify which skills will help the AI agent
- After brainstorming an app idea and before implementation begins
- User asks to propose skills based on a PRD or project description
- Evaluating what context the AI agent will need for optimal performance
Critical Patterns
- ALWAYS ask clarifying questions if tech stack is unclear — never guess
- Prioritize hallucination-prone technologies — React, Next.js, FastAPI, etc. change frequently
- Security-focused skills are always High priority — auth, validation, encryption
- Link must point to actual URL found or use "—" (never invent URLs)
- User is responsible for skill verification — always show security warning
Decision Trees
When to Ask Questions vs Proceed
| Situation |
Action |
| Primary language identified |
Proceed |
| Framework(s) identified |
Proceed |
| Database identified |
Proceed |
| Architecture type known |
Proceed |
| Any of above missing |
ASK before proceeding |
How to Determine Priority
| Condition |
Priority |
| Core technology + changes frequently |
High |
| Security-related (auth, encryption) |
High |
| Complex API / syntax |
High |
| Important but stable |
Medium |
| Good public documentation exists |
Medium |
| Nice-to-have or very stable |
Low |
When to Include a Link
| Situation |
Link Field |
| Found excellent match in skillsmp.com |
Full URL |
| Found excellent match in skills.sh |
Full URL |
| Found relevant Context7 docs |
— (mention in notes) |
| No search performed |
— |
| No good match found |
— |
Workflow
Phase 0: Clarification (If Needed)
Before analyzing, assess whether the project description is clear enough. Ask the user questions if:
Tech stack is unclear or ambiguous
- "Which programming language(s) do you plan to use?"
- "Which framework(s) are you considering for the frontend/backend?"
Architecture decisions are missing
- "Are you planning a monolithic architecture, microservices, or serverless?"
- "What type of database are you planning to use?"
Scale and complexity are unknown
- "Is this a personal project, startup MVP, or enterprise application?"
- "Do you need authentication, authorization, or multi-tenancy?"
Quality requirements are not specified
- "What level of test coverage are you aiming for?"
- "Do you have specific performance requirements?"
Important: Ask questions BEFORE proceeding with analysis.
Phase 1: Tech Stack Analysis
Identify and document:
- Programming languages and specific versions
- Frameworks and core libraries (frontend, backend, mobile...)
- Databases and persistence solutions
- Infrastructure and deployment (Docker, Kubernetes, CI/CD...)
- Development tools (testing, linting, build tools...)
Phase 2: Pattern and Architecture Analysis
- Architecture type (monolith, microservices, serverless, event-driven...)
- Relevant development patterns (TDD, DDD, SDD, Clean Architecture, Hexagonal...)
- Quality requirements (testing, security, performance, observability)
- Applicable conventions and standards
Phase 3: Skill Needs Identification
For each technology, pattern, or process identified, ask yourself:
- Does this technology change frequently? → Needs updated skill
- Does it have complex syntax or APIs? → Needs skill with examples
- Is it critical for project success? → High priority
- Can the agent easily hallucinate here? → Needs specific context
Phase 4: Existing Skills Search (Optional)
If considered useful, search in:
Output Format
Present a table with the proposed skills:
| Skill |
Technology/Process |
Reason |
Priority |
Link |
| Descriptive name |
Technology or process covered |
Brief justification |
High/Medium/Low |
URL or "—" |
Security Warning
⚠️ IMPORTANT — User Responsibility:
Before adding any skill to your project:
- Read the complete code of the downloaded skill
- Verify it contains no prompt injection or malicious instructions
- Understand what permissions it has and which tools it can use
- Confirm it comes from a trusted source
The agent can propose, but you decide which skills to use. Skills are added manually under your responsibility.
Delegation to skill-creator
If the user requests to create a custom skill instead of using an existing one:
"To create this skill, use the skill-creator skill which will guide you through the generation process."
Do not create skills directly from this skill. Only identify needs and propose.
Resources
- Skills Marketplaces: skillsmp.com, skills.sh
- Documentation Lookup: Context7 MCP for up-to-date library documentation
- Skill Creation: Use
skill-creator skill to generate custom skills
Usage Example
User input:
"I'm going to develop a REST API with FastAPI, PostgreSQL, and JWT authentication. The frontend will be React with TypeScript."
Expected output:
Remember: Review each skill's complete code before adding it to your project. The links are suggestions — always verify the content.
1---2name: skill-proposer3description: When to Use4---56## When to Use78Use this skill when:910- Starting a new project and need to identify which skills will help the AI agent11- After brainstorming an app idea and before implementation begins12- User asks to propose skills based on a PRD or project description13- Evaluating what context the AI agent will need for optimal performance1415---1617## Critical Patterns1819- **ALWAYS ask clarifying questions** if tech stack is unclear — never guess20- **Prioritize hallucination-prone technologies** — React, Next.js, FastAPI, etc. change frequently21- **Security-focused skills are always High priority** — auth, validation, encryption22- **Link must point to actual URL found** or use "—" (never invent URLs)23- **User is responsible for skill verification** — always show security warning2425---2627## Decision Trees2829### When to Ask Questions vs Proceed3031| Situation | Action |32|-----------|--------|33| Primary language identified | Proceed |34| Framework(s) identified | Proceed |35| Database identified | Proceed |36| Architecture type known | Proceed |37| **Any of above missing** | **ASK before proceeding** |3839### How to Determine Priority4041| Condition | Priority |42|-----------|----------|43| Core technology + changes frequently | High |44| Security-related (auth, encryption) | High |45| Complex API / syntax | High |46| Important but stable | Medium |47| Good public documentation exists | Medium |48| Nice-to-have or very stable | Low |4950### When to Include a Link5152| Situation | Link Field |53|-----------|------------|54| Found excellent match in skillsmp.com | Full URL |55| Found excellent match in skills.sh | Full URL |56| Found relevant Context7 docs | — (mention in notes) |57| No search performed | — |58| No good match found | — |5960---6162## Workflow6364### Phase 0: Clarification (If Needed)6566Before analyzing, assess whether the project description is clear enough. **Ask the user questions** if:6768- **Tech stack is unclear or ambiguous**69 - "Which programming language(s) do you plan to use?"70 - "Which framework(s) are you considering for the frontend/backend?"71 72- **Architecture decisions are missing**73 - "Are you planning a monolithic architecture, microservices, or serverless?"74 - "What type of database are you planning to use?"75 76- **Scale and complexity are unknown**77 - "Is this a personal project, startup MVP, or enterprise application?"78 - "Do you need authentication, authorization, or multi-tenancy?"79 80- **Quality requirements are not specified**81 - "What level of test coverage are you aiming for?"82 - "Do you have specific performance requirements?"8384**Important**: Ask questions BEFORE proceeding with analysis.8586### Phase 1: Tech Stack Analysis8788Identify and document:8990- **Programming languages** and specific versions91- **Frameworks and core libraries** (frontend, backend, mobile...)92- **Databases** and persistence solutions93- **Infrastructure and deployment** (Docker, Kubernetes, CI/CD...)94- **Development tools** (testing, linting, build tools...)9596### Phase 2: Pattern and Architecture Analysis9798- Architecture type (monolith, microservices, serverless, event-driven...)99- Relevant development patterns (TDD, DDD, SDD, Clean Architecture, Hexagonal...)100- Quality requirements (testing, security, performance, observability)101- Applicable conventions and standards102103### Phase 3: Skill Needs Identification104105For each technology, pattern, or process identified, ask yourself:1061071. **Does this technology change frequently?** → Needs updated skill1082. **Does it have complex syntax or APIs?** → Needs skill with examples1093. **Is it critical for project success?** → High priority1104. **Can the agent easily hallucinate here?** → Needs specific context111112### Phase 4: Existing Skills Search (Optional)113114If considered useful, search in:115116- **https://skillsmp.com/** — Skills marketplace117- **https://skills.sh/** — Skills marketplace118- **Context7** — MCP for up-to-date library documentation119120---121122## Output Format123124Present a table with the proposed skills:125126| Skill | Technology/Process | Reason | Priority | Link |127|-------|-------------------|--------|----------|------|128| Descriptive name | Technology or process covered | Brief justification | High/Medium/Low | URL or "—" |129130---131132## Security Warning133134⚠️ **IMPORTANT — User Responsibility**:135136Before adding any skill to your project:1371381. **Read the complete code** of the downloaded skill1392. **Verify it contains no prompt injection** or malicious instructions1403. **Understand what permissions it has** and which tools it can use1414. **Confirm it comes from a trusted source**142143The agent can propose, but **you decide** which skills to use. Skills are added manually under your responsibility.144145---146147## Delegation to skill-creator148149If the user requests to create a custom skill instead of using an existing one:150151> "To create this skill, use the `skill-creator` skill which will guide you through the generation process."152153Do not create skills directly from this skill. Only identify needs and propose.154155---156157## Resources158159- **Skills Marketplaces**: [skillsmp.com](https://skillsmp.com/es), [skills.sh](https://skills.sh/)160- **Documentation Lookup**: Context7 MCP for up-to-date library documentation161- **Skill Creation**: Use `skill-creator` skill to generate custom skills162163---164165## Usage Example166167**User input**:168> "I'm going to develop a REST API with FastAPI, PostgreSQL, and JWT authentication. The frontend will be React with TypeScript."169170**Expected output**:171172| Skill | Technology/Process | Reason | Priority | Link |173|-------|-------------------|--------|----------|------|174| fastapi-best-practices | FastAPI | Framework with specific patterns and frequent updates | High | https://skills.sh/wshobson/agents/fastapi-templates |175| pydantic-validation | Pydantic | Core data validation in FastAPI, syntax changes between versions | High | — |176| jwt-auth-python | JWT + Python | Auth implementation prone to security errors | High | https://skills.sh/mindrally/skills/jwt-security |177| sqlalchemy-modern | SQLAlchemy + PostgreSQL | ORM with syntax that varies between versions | High | — |178| react-typescript-patterns | React + TypeScript | Modern hooks patterns, generic types | High | https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices |179| testing-fastapi | pytest + FastAPI | API testing with specific fixtures and mocks | Medium | — |180| docker-python | Dockerfile Python | Image optimization, multi-stage builds | Medium | https://skillsmp.com/es/skills/affaan-m-everything-claude-code-kiro-skills-docker-patterns-skill-md |181| git-conventions | Git workflow | Conventional commits, branching strategy | Low | — |182183---184185**Remember**: Review each skill's complete code before adding it to your project. The links are suggestions — always verify the content.
Pablo-Lozano-Gil